On the Explainability of Graph Convolutional Network With GCN Tangent Kernel

DOI10.1162/NECO_A_01548MaRDI QIDQ5059719zbMATH OpenOpenAlexFDO

Authors Xianchen Zhou, Hongxia Wang

Publication date 16 January 2023

Published in Neural Computation (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1162/neco_a_01548

Mathematics Subject Classification ID

Computer science (68-XX)

Recommendations

• The logic of graph neural networks
• Geometric deep learning: a temperature based analysis of graph neural networks
• Lower and upper bounds for numbers of linear regions of graph convolutional networks
• Mg-SubAgg: multi-granularity subgraph aggregation with topology for GNN
• Transferability of graph neural networks: an extended graphon approach

Cites work

• Phase diagram for two-layer ReLU neural networks at infinite-width limit
• The Vapnik-Chervonenkis dimension of graph and recursive neural networks

Cited in

(5)

• Transferability of graph neural networks: an extended graphon approach
• Complex exponential graph convolutional networks
• Mg-SubAgg: multi-granularity subgraph aggregation with topology for GNN
• \texttt{GIST}: distributed training for large-scale graph convolutional networks
• A tighter generalization error bound for wide GCN based on loss landscape

Describes a project that uses

Uses Software

• GNNExplainer

This page was built for publication: On the Explainability of Graph Convolutional Network With GCN Tangent Kernel

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5059719)